© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14799
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大åݦ
    -0.20
    èĢģæŧ
    -0.20
    tie
    -0.19
    æĸ°åĵģ
    -0.19
    eties
    -0.19
    ìĦ¸
    -0.18
     Wet
    -0.18
     Newspaper
    -0.18
    æĬ¥çº¸
    -0.18
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.18
    POSITIVE LOGITS
    æīĭæľºåı·
    0.23
    åİĭæĬij
    0.22
    纹
    0.21
    æĭ¼åij½
    0.20
    çŁ³æ¦´
    0.20
    ħĮ
    0.19
    =username
    0.19
    çªģåĩºéĹ®é¢ĺ
    0.19
    æĺ¯ä¸ĢåIJį
    0.19
    สะà¸Ķวà¸ģ
    0.19
    Activations Density 0.009%

    No Known Activations